Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Improving Variational Autoencoders for New Physics Detection at the LHC With Normalizing Flows

Journal Article · · Frontiers in Big Data
 [1];  [1];  [1];  [1];  [2];  [3];  [4];  [4]
  1. European Organization for Nuclear Research (CERN), Geneva (Switzerland)
  2. European Organization for Nuclear Research (CERN), Geneva (Switzerland); Univ. of Vienna (Austria)
  3. Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States); California Institute of Technology (CalTech), Pasadena, CA (United States)
  4. Univ. of California, San Diego, CA (United States)
+ Show Author Affiliations

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

Research Organization:
Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC), High Energy Physics (HEP); European Research Council (ERC)
Grant/Contract Number:
AC02-07CH11359; SC0021187
OSTI ID:
1833285
Report Number(s):
FERMILAB-PUB-21-519-CMS; arXiv:2110.08508; oai:inspirehep.net:1946088
Journal Information:
Frontiers in Big Data, Journal Name: Frontiers in Big Data Vol. 5; ISSN 2624-909X
Publisher:
FrontiersCopyright Statement
Country of Publication:
United States
Language:
English

References (35)

Unsupervised-Hackathon dataset January 2020
High-dimensional Anomaly Detection with Radiative Return in e+e- Collisions dataset January 2021
A Family of Nonparametric Density Estimation Algorithms journal September 2012
Tag N’ Train: a technique to train improved classifiers on unlabeled data journal January 2021
Variational autoencoders for new physics mining at the Large Hadron Collider journal May 2019
Quasi anomalous knowledge: searching for new physics with embedded knowledge journal June 2021
Autoencoders for unsupervised anomaly detection in high energy physics journal June 2021
Adversarially-trained autoencoders for robust unsupervised new physics searches journal October 2019
Learning the latent structure of collider events journal October 2020
Graph neural networks: A review of methods and applications journal January 2020
A general search for new phenomena at HERA journal April 2009
The LHC Olympics 2020 a community challenge for anomaly detection in high energy physics journal December 2021
The CMS High Level Trigger journal June 2014
Operation of the ATLAS trigger system in Run 2 journal October 2020
Performance of the CMS Level-1 trigger in proton-proton collisions at √ s = 13 TeV journal October 2020
Graph neural networks in particle physics journal January 2021
Searching for new physics with deep autoencoders journal April 2020
Anomaly detection with density estimation journal April 2020
Novelty detection meets collider physics journal April 2020
Simulation assisted likelihood-free anomaly detection journal May 2020
Classifying anomalies through outer density estimation journal September 2022
Global search for new physics with 2.0     fb − 1 at CDF journal January 2009
Model independent search for new phenomena in p p ¯ collisions at s = 1.96     TeV journal May 2012
Extending the search for new resonances with machine learning journal January 2019
Learning new physics from a machine journal January 2019
Anomaly Detection for Resonant New Physics with Machine Learning journal December 2018
Geometric Deep Learning: Going beyond Euclidean data journal July 2017
Normalizing Flows: An Introduction and Review of Current Methods journal January 2020
Trial factors for the look elsewhere effect in high energy physics journal October 2010
A strategy for a general search for new phenomena using data-derived signal regions and its application within the ATLAS experiment journal February 2019
Guiding new physics searches with unsupervised learning journal March 2019
Learning multivariate new physics journal January 2021
Comparing weak- and unsupervised methods for resonant anomaly detection journal July 2021
QCD or what? journal January 2019
Density estimation by dual ascent of the log-likelihood journal January 2010

Similar Records

Fast Particle-based Anomaly Detection Algorithm with Variational Autoencoder
Journal Article · Mon Nov 27 23:00:00 EST 2023 · TBD · OSTI ID:2282460
Challenges for unsupervised anomaly detection in particle physics
Journal Article · Tue Mar 08 23:00:00 EST 2022 · Journal of High Energy Physics (Online) · OSTI ID:1976605

Related Subjects

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
Large Hadron Collider (LHC)
anomaly detection (AD)
convolutional neural net
graph convolutional network (GCN)
new physics beyond standard model
normalizing flow (NF)
variational auto encoder (VAE)